1 / 12

Chapter 1

Chapter 1. Descriptive Analysis. Statistics – Making sense out of data. Gives verifiable evidence to support the answer to a question. 4 Major Parts Collecting Data – Define a good question, do Comparative Experiment or Sampling from a population

inoke
Download Presentation

Chapter 1

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Chapter 1 Descriptive Analysis

  2. Statistics – Making sense out of data. Gives verifiable evidence to support the answer to a question. 4 Major Parts • Collecting Data – Define a good question, do Comparative Experiment or Sampling from a population • Descriptive Analysis – Describes your observations using numbers, tables, charts, and graphs – look for trends or relationships • Probability – Tells us how confident we can be in our results. • Inference – Making decisions or predictions based on the data and probability

  3. Collecting Data: A refined problem statement and good design for data collection are critical. • Ask yourself the following questions before you begin collecting data. • What am I trying to show (prove)? • How many units or subjects shall I collect data from? • How shall I select these units or individuals to be studied?

  4. Descriptive Analysis: Variable – a characteristic of the unit or subject being studied. Two main types: qualitative and quantitative -Qualitative or Categorical – concerned with the quality of a unit. Observations fall into separate distinct categories. -breaks down into two sub-types: ordinal or nominal -ordinal – if an ordering exists eg. number of cars sold per year (years are categories), socio-economic status (low, middle, high class) by income etc. -nominal – if there is no natural order between the categories (eg. Eye color, ice cream flavors, etc.) Such data are inherently discrete - the numbers take on only certain values in some range they are usually counts – whole #s (you don’t usually have a fraction of a person with brown eyes)

  5. Quantitative or Numerical – usually measures quantities: (eg. heights, distances etc.) these are said to be -Continuous – numbers can take on all values within some range But quantitative data can also be -Discrete- the numbers take on only certain values in some range (eg. Age, test scores, etc.) These are countable numbers, whole numbers For examples of Qualitative (discrete) and Quantitative (continuous or discrete) follow this link http://www.gvsu.edu/stat/index.cfm?id=3B35E089-AD5B-2CE7-A84A49BD81A691EB

  6. Bivariate data – two variables, Explanatory (Independent) and Response (Dependent) Shows a correlation or cause and effect between two variables. Ex. Distance vs. time or temperature vs. pressure etc. Scatter plots and line graphs are usually used with bivariate data. • Univariate data – one variable (one characteristic of a subject or unit) Distribution graphs are used with univariate data.

  7. Distribution graphs- display the distribution of one characteristic of a subject or unit, it tells us what values the variable takes and how often it takes these values (frequency the data falls into each interval) (Ex. Liters machine fills each pop bottle in 3 seconds)

  8. Types of distribution graphs: Used with Continuous Data • Histograms – used with larger sets of data >20 • Dot plots - used with smaller sets of data <20 • Stem and Leaf plots – smaller sets of data <20 • Box & whisker plots- larger sets of data >20 Used with Discrete Data • Pie Graphs • Bar Graphs

  9. Describing Distributions Measures of Shape, Center and Spread • Shape – Symmetric, Skewed, Bimodal, Multimodal, Bell, Gaps etc. • Center – Mean, Median, Mode • Mean – arithmetic average of all data Ë = 1/n Æxi • non resistant measure of center – outlier will pull mean towards itself -Median- middle number in an ordered set of numbers resistant measure of center not sensitive to outliers **If mean = median then distribution is symmetric -Mode- most common data point

  10. Measures of Spread and Variability • Range = Max – Min • Inner Quartile Range, IQR, Q3-Q1 middle 50% of data. (used with any dist.) • Variance – a measure of how data varies • S2 = 1/(n-1) Æ(x1-Ë)2 • Standard Deviation – the average deviation or distance data lie above or below the mean (used with symmetric dist.) • S = ð1/(n-1) Æ(x1-Ë)2

  11. Outlier – an observation or point that lies outside the overall pattern of the data Outlier Analysis • for either Skewed or Symmetric Distributions use 1.5(IQR) added to the Q3 and subtracted from Q1. • For only Symmetric Distribution use 3 x standard deviation above and below the mean. • Lets do #10 page 20 together Assign: page 16 #s 5 and 6 page 42 #s 31,32, 33

More Related